384 citations · 1.3k across the 26 of their papers we have counts for
5 papers · 1 filter
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
Zhanpeng Zhou, Yongyi Yang, Xiaojiang Yang +2
Recent work has revealed many intriguing empirical phenomena in neural network training, despite the poorly understood and highly complex loss landscapes and training dynamics. One…
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
Yongyi Yang, Jacob Steinhardt, Wei Hu
Recent work has observed an intriguing ''Neural Collapse'' phenomenon in well-trained neural networks, where the last-layer representations of training samples with the same label…
The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks
Can Yaras, Peng Wang, Wei Hu +3
Over the past few years, an extensively studied phenomenon in training deep networks is the implicit bias of gradient descent towards parsimonious solutions. In this work, we inves…
Sparse Mean Estimation in Adversarial Settings via Incremental Learning
Jianhao Ma, Rui Ray Chen, Yinghui He +2
In this paper, we study the problem of sparse mean estimation under adversarial corruptions, where the goal is to estimate the -sparse mean of a heavy-tailed distribution from s…
Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning
Xiangrong Zhu, Guangyao Li, Wei Hu
Federated Learning (FL) recently emerges as a paradigm to train a global machine learning model across distributed clients without sharing raw data. Knowledge Graph (KG) embedding…